mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-03-09 10:39:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix(cli): avoid runtime __origin__ check for older Python (#798)

Browse Source 
fix(cli): avoid runtime __origin__ on older Python

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
This commit is contained in:
Aaron Pham
2023-12-18 12:33:36 -05:00
committed by GitHub
parent 37dbccc3d7
commit 5d27337e82
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
openllm-python/src/openllm_cli/entrypoint.py
View File

@@ -363,7 +363,7 @@ def start_command(
elif dtype not in {'float', 'float32'}:
logger.warning('"bfloat16" and "half" are not supported on CPU. OpenLLM will default fallback to "float32".')
dtype = 'float' # we need to cast back to full precision if cuda is not available
llm = openllm.LLM[t.Any, t.Any](
llm = openllm.LLM(
model_id=model_id,
model_version=model_version,
backend=backend,
@@ -590,7 +590,7 @@ def import_command(
fg='yellow',
)
llm = openllm.LLM[t.Any, t.Any](
llm = openllm.LLM(
model_id=model_id,
model_version=model_version,
quantize=quantize,
@@ -769,7 +769,7 @@ def build_command(
if backend == 'pt':
logger.warning("PyTorch backend is deprecated and will be removed from the next releases. Will set default backend to 'vllm' instead.")
llm = openllm.LLM[t.Any, t.Any](
llm = openllm.LLM(
model_id=model_id,
model_version=model_version,
backend=backend,